An actor-critic algorithm with a Monte Carlo risk critic is proposed for optimizing reinforcement learning policies under arbitrary, possibly non-coherent risk measures, with a risk function fitted from simulated data.
Existence and Finiteness Conditions for Risk-Sensitive Planning: Results and Conjectures
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Decision-theoretic planning with risk-sensitive planning objectives is important for building autonomous agents or decision-support systems for real-world applications. However, this line of research has been largely ignored in the artificial intelligence and operations research communities since planning with risk-sensitive planning objectives is more complicated than planning with risk-neutral planning objectives. To remedy this situation, we derive conditions that guarantee that the optimal expected utilities of the total plan-execution reward exist and are finite for fully observable Markov decision process models with non-linear utility functions. In case of Markov decision process models with both positive and negative rewards, most of our results hold for stationary policies only, but we conjecture that they can be generalized to non stationary policies.
fields
cs.LG 1years
2019 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Practical Risk Measures in Reinforcement Learning
An actor-critic algorithm with a Monte Carlo risk critic is proposed for optimizing reinforcement learning policies under arbitrary, possibly non-coherent risk measures, with a risk function fitted from simulated data.